ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control
ARB4WM:连续控制中世界模型的对抗鲁棒性基准
机构 * College of Computer Science, National University of Defense Technology(国防科技大学计算机学院) ; College of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院) ; Department of New Networks, Peng Cheng Laboratory(鹏城实验室新型网络部) ; National Key Laboratory of Advanced Communication Networks(先进通信网络全国重点实验室)
专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)
AI总结 提出ARB4WM统一基准,从策略、价值和潜在动力学三个层面评估世界模型在视觉扰动下的对抗鲁棒性,发现多目标攻击和时序暴露模式对安全评估至关重要。
Comments 24 pages, 10 figures, 5 tables. Source code available at https://github.com/zaoanguai/ARB4WM